Betrayed by Motion: Camouflaged Object Discovery via Motion Segmentation
This work is significant for computer vision researchers working on object discovery and segmentation in challenging scenarios, particularly for camouflaged objects, by introducing a new dataset and method.
This paper addresses the problem of discovering camouflaged objects in videos by exploiting motion information. The authors propose a novel architecture with a differentiable registration module and a motion segmentation module with memory, demonstrating its effectiveness on a new large-scale dataset (MoCA) and achieving competitive performance on DAVIS2016 for unsupervised segmentation.
The objective of this paper is to design a computational architecture that discovers camouflaged objects in videos, specifically by exploiting motion information to perform object segmentation. We make the following three contributions: (i) We propose a novel architecture that consists of two essential components for breaking camouflage, namely, a differentiable registration module to align consecutive frames based on the background, which effectively emphasises the object boundary in the difference image, and a motion segmentation module with memory that discovers the moving objects, while maintaining the object permanence even when motion is absent at some point. (ii) We collect the first large-scale Moving Camouflaged Animals (MoCA) video dataset, which consists of over 140 clips across a diverse range of animals (67 categories). (iii) We demonstrate the effectiveness of the proposed model on MoCA, and achieve competitive performance on the unsupervised segmentation protocol on DAVIS2016 by only relying on motion.